Enhancing accuracy and convenience of golf swing tracking with a wrist-worn single inertial sensor

In this study, we address two technical challenges to enhance golf swing trajectory accuracy using a wrist-worn inertial sensor: orientation estimation and drift error mitigation. We extrapolated consistent sensor orientation from specific address-phase signal segments and trained the estimation with a convolutional neural network. We then mitigated drift error by applying a constraint on wrist speed at the address, backswing top, and finish, and ensuring that the wrist's finish displacement aligns with a virtual circle on the 3D swing plane. To verify the proposed methods, we gathered data from twenty male right-handed golfers, including professionals and amateurs, using a driver and a 7-iron. The orientation estimation error was about 60% of the baseline, comparable to studies requiring additional sensor information or calibration poses. The drift error was halved and the single-inertial-sensor tracking performance across all swing phases was about 17 cm, on par with multimodal approaches. This study introduces a novel signal processing method for tracking rapid, wide-ranging motions, such as a golf swing, while maintaining user convenience. Our results could impact the burgeoning field of daily motion monitoring for health care, especially with the increasing prevalence of wearable devices like smartwatches.

Experimental investigation of drag loss behavior of dip-lubricated wet clutches for building a data-driven prediction model

Fundamental knowledge of wet clutches' drag loss behavior is essential for designing low-loss clutch systems. In contrast to the widely investigated injection lubrication, more comprehensive knowledge is needed on the drag loss behavior of dip-lubricated wet clutches. In the development phase, data-driven models allow drag loss predictions with low computational effort and, at the same time, sufficient accuracy. Therefore, this study aimed to deepen and expand knowledge of the drag loss behavior of dip-lubricated wet clutches based on experimental investigations. Moreover, the investigations were designed and conducted so that the generated data and findings can be used in further research for building data-driven prediction models. The investigations were conducted on two clutch systems from automotive and industrial applications. The practice-relevant parameters of clearance, oil level, oil viscosity, and plate shape were investigated based on a mixed-level full factorial design. The evaluation shows that a reduction in drag loss can be achieved primarily by increasing the clearance, reducing the oil viscosity, and choosing waved plates. The obtained drag loss behavior can be traced back to the form of oil displacement from the gaps. The displacement process, in turn, is influenced by the operating and geometry parameters. Although the flow in the gaps develops differently for dip and injection lubrication over differential speed, the study shows comparable integral effects of the influencing parameters for both types of lubrication. The generated datasets contain the investigated parameters as features and characteristic drag loss values as targets. The findings can support the selection and configuration of the machine learning algorithm and the validation of the trained models. The described procedure can serve as a template for generating and analyzing datasets for data-driven modeling of wet clutches' drag losses.

A novel method-based reinforcement learning with deep temporal difference network for flexible double shop scheduling problem

This paper studies the flexible double shop scheduling problem (FDSSP) that considers simultaneously job shop and assembly shop. It brings about the problem of scheduling association of the related tasks. To this end, a reinforcement learning algorithm with a deep temporal difference network is proposed to minimize the makespan. Firstly, the FDSSP is defined as the mathematical model of the flexible job-shop scheduling problem joined to the assembly constraint level. It is translated into a Markov decision process that directly selects behavioral strategies according to historical machining state data. Secondly, the proposed ten generic state features are input into the deep neural network model to fit the state value function. Similarly, eight simple constructive heuristics are used as candidate actions for scheduling decisions. From the greedy mechanism, optimally combined actions of all machines are obtained for each decision step. Finally, a deep temporal difference reinforcement learning framework is established, and a large number of comparative experiments are designed to analyze the basic performance of this algorithm. The results showed that the proposed algorithm was better than most other methods, which contributed to solving the practical production problem of the manufacturing industry.

Convolutional spiking neural networks for intent detection based on anticipatory brain potentials using electroencephalogram

Spiking neural networks (SNNs) are receiving increased attention because they mimic synaptic connections in biological systems and produce spike trains, which can be approximated by binary values for computational efficiency. Recently, the addition of convolutional layers to combine the feature extraction power of convolutional networks with the computational efficiency of SNNs has been introduced. This paper studies the feasibility of using a convolutional spiking neural network (CSNN) to detect anticipatory slow cortical potentials (SCPs) related to braking intention in human participants using an electroencephalogram (EEG). Data was collected during an experiment wherein participants operated a remote-controlled vehicle on a testbed designed to simulate an urban environment. Participants were alerted to an incoming braking event via an audio countdown to elicit anticipatory potentials that were measured using an EEG. The CSNN's performance was compared to a standard CNN, EEGNet and three graph neural networks via 10-fold cross-validation. The CSNN outperformed all the other neural networks, and had a predictive accuracy of 99.06% with a true positive rate of 98.50%, a true negative rate of 99.20% and an F1-score of 0.98. Performance of the CSNN was comparable to the CNN in an ablation study using a subset of EEG channels that localized SCPs. Classification performance of the CSNN degraded only slightly when the floating-point EEG data were converted into spike trains via delta modulation to mimic synaptic connections.

A soft cable loop based gripper for robotic automation of chemistry

Robotic automation is proving itself indispensable in the modern Chemistry laboratory, but adoption is slowed down by the technical challenges of implementing such systems. This paper reports on a novel adaptive gripper mechanism that can easily and reliably grasp cylindrical and prismatic objects of various sizes with limited clearance required. The proposed design exploits the inherent compliance of a cable that is driven to fully envelope the target object. The cable is run through a rigid finger, allowing the loop to be placed around objects with minimal clearance required and to provide support for the object once the grip is complete. Thanks to the compliant nature of the mechanism, the gripper requires minimal control effort to complete a gasping task. A prototype of the gripper has been designed and built for chemistry automation tasks, where it showed very high grasp reliability with ≤ 1 % grasp failures.

A six degrees-of-freedom cable-driven robotic platform for head-neck movement

This paper introduces a novel cable-driven robotic platform that enables six degrees-of-freedom (DoF) natural head-neck movements. Poor postural control of the head-neck can be a debilitating symptom of neurological disorders such as amyotrophic lateral sclerosis and cerebral palsy. Current treatments using static neck collars are inadequate, and there is a need to develop new devices to empower movements and facilitate physical rehabilitation of the head-neck. State-of-the-art neck exoskeletons using lower DoF mechanisms with rigid linkages are limited by their hard motion constraints imposed on head-neck movements. By contrast, the cable-driven robot presented in this paper does not constrain motion and enables wide-range, 6-DoF control of the head-neck. We present the mechatronic design, validation, and control implementations of this robot, as well as a human experiment to demonstrate a potential use case of this versatile robot for rehabilitation. Participants were engaged in a target reaching task while the robot applied both assistive and resistive moments on the head during the task. Our results show that neck muscle activation increased by 19% when moving the head against resistance and decreased by 28-43% when assisted by the robot. Overall, these results provide a scientific justification for further research in enabling movement and identifying personalized rehabilitation for motor training. Beyond rehabilitation, other applications such as applying force perturbations on the head to study sensory integration and applying traction to achieve pain relief may benefit from the innovation of this robotic platform which is capable of applying controlled 6-DoF forces/moments on the head.

Programmable photoacoustic patterning of microparticles in air

Optical and acoustic tweezers, despite operating on different physical principles, offer non-contact manipulation of microscopic and mesoscopic objects, making them essential in fields like cell biology, medicine, and nanotechnology. The advantages and limitations of optical and acoustic manipulation complement each other, particularly in terms of trapping size, force intensity, and flexibility. We use photoacoustic effects to generate localized Lamb wave fields capable of mapping arbitrary laser pattern shapes. By using localized Lamb waves to vibrate the surface of the multilayer membrane, we can pattern tens of thousands of microscopic particles into the desired pattern simultaneously. Moreover, by quickly and successively adjusting the laser shape, microparticles flow dynamically along the corresponding elastic wave fields, creating a frame-by-frame animation. Our approach merges the programmable adaptability of optical tweezers with the potent manipulation capabilities of acoustic waves, paving the way for wave-based manipulation techniques, such as microparticle assembly, biological synthesis, and microsystems.

Powder-size driven facile microstructure control in powder-fusion metal additive manufacturing processes

Microstructure control in metal additive manufacturing is highly desirable for superior and bespoke mechanical performance. Engineering the columnar-to-equiaxed transition during rapid solidification in the additive manufacturing process is crucial for its technological advancement. Here, we report a powder-size driven melt pool engineering approach, demonstrating facile and large-scale control in the grain morphology by triggering a counterintuitive response of powder size to the additively manufactured 316 L stainless steel microstructure. We obtain coarse-grained (>100 μm) or near-monocrystalline microstructure using fine powders and near-equiaxed, fine-grained (<10 μm) microstructure using coarse powders. This approach shows resourceful adaptability to directed energy deposition and powder-bed fusion with no added cost, where the particle-size dependent powder-flow preheating effects and powder-bed thermophysical properties drive the microstructural variations. This work presents a pathway for leveraging feedstock particle size distribution towards more controllable, cost-effective, and sustainable metal additive manufacturing.

Fabrication of glass/madar fibers reinforced hybrid epoxy composite: a comprehensive study on the material stability

The present study aims to examine the characteristics of a composite material composed of glass/madar fibers and porcelain particles, which are reinforced with epoxy. A compression molding technique achieves the fabrication of this composite. A comprehensive characterization was conducted by employing a mixture of analytical techniques, including X-ray Diffraction (XRD), mechanical testing, Scanning Electron Microscopy (SEM), Dynamic Mechanical Analysis (DMA), and Thermogravimetric Analysis (TGA). The composition of the composite was determined using X-ray diffraction (XRD) analysis, which demonstrated the successful integration of porcelain fillers. The material exhibited notable mechanical properties, rendering it appropriate for utilization in structural applications. The utilization of SEM facilitated the examination of the microstructure of the composite material, thereby providing a deeper understanding of the interactions between the fibers and the matrix. DMA results revealed the glass/madar composite contained 4.2% higher viscoelastic properties when the addition of porcelain filler, thermal stability was improved up to the maximum temperature of 357 °C. This study provided significant insights into the properties of a hybrid epoxy composite consisting of glass/madar fibers reinforced porcelain particles.

Zero modes activation to reconcile floppiness, rigidity, and multistability into an all-in-one class of reprogrammable metamaterials

Existing mechanical metamaterials are typically designed to either withstand loads as a stiff structure, shape morph as a floppy mechanism, or trap energy as a multistable matter, distinct behaviours that correspond to three primary classes of macroscopic solids. Their stiffness and stability are sealed permanently into their architecture, mostly remaining immutable post-fabrication due to the invariance of zero modes. Here, we introduce an all-in-one reprogrammable class of Kagome metamaterials that enable the in-situ reprogramming of zero modes to access the apparently conflicting properties of all classes. Through the selective activation of metahinges via self-contact, their architecture can be switched to acquire on-demand rigidity, floppiness, or global multistability, bridging the seemingly uncrossable gap between structures, mechanisms, and multistable matters. We showcase the versatile generalizations of the metahinge and remarkable reprogrammability of zero modes for a range of properties including stiffness, mechanical signal guiding, buckling modes, phonon spectra, and auxeticity, opening a plethora of opportunities for all-in-one materials and devices.

Flexible calorimetric flow sensor with unprecedented sensitivity and directional resolution for multiple flight parameter detection

The accurate perception of multiple flight parameters, such as the angle of attack, angle of sideslip, and airflow velocity, is essential for the flight control of micro air vehicles, which conventionally rely on arrays of pressure or airflow velocity sensors. Here, we present the estimation of multiple flight parameters using a single flexible calorimetric flow sensor featuring a sophisticated structural design with a suspended array of highly sensitive vanadium oxide thermistors. The proposed sensor achieves an unprecedented velocity resolution of 0.11 mm·s-1 and angular resolution of 0.1°. By attaching the sensor to a wing model, the angles of attack and slip were estimated simultaneously. The triaxial flight velocities and wing vibrations can also be estimated by sensing the relative airflow velocity due to its high sensitivity and fast response. Overall, the proposed sensor has many promising applications in weak airflow sensing and flight control of micro air vehicles.

Automated detection and classification of concealed objects using infrared thermography and convolutional neural networks

This paper presents a study on the effectiveness of a convolutional neural network (CNN) in classifying infrared images for security scanning. Infrared thermography was explored as a non-invasive security scanner for stand-off and walk-through concealed object detection. Heat generated by human subjects radiates off the clothing surface, allowing detection by an infrared camera. However, infrared lacks in penetration capability compared to longer electromagnetic waves, leading to less obvious visuals on the clothing surface. ResNet-50 was used as the CNN model to automate the classification process of thermal images. The ImageNet database was used to pre-train the model, which was further fine-tuned using infrared images obtained from experiments. Four image pre-processing approaches were explored, i.e., raw infrared image, subject cropped region-of-interest (ROI) image, K-means, and Fuzzy-c clustered images. All these approaches were evaluated using the receiver operating characteristic curve on an internal holdout set, with an area-under-the-curve of 0.8923, 0.9256, 0.9485, and 0.9669 for the raw image, ROI cropped, K-means, and Fuzzy-c models, respectively. The CNN models trained using various image pre-processing approaches suggest that the prediction performance can be improved by the removal of non-decision relevant information and the visual highlighting of features.

Bubble dynamics and atomization of acoustically levitated diesel and biodiesel droplets using femtosecond laser pulses

This study focuses on the bubble dynamics and associated breakup of individual droplets of diesel and biodiesel under the influence of femtosecond laser pulses. The bubble dynamics were examined by suspending the droplets in the air through an acoustically levitated setup. The laser pulse energies ranged from 25 to 1050 µJ, and droplet diameters varied between 0.25 and 1.5 mm. High-speed shadowgraphy was employed to examine the influence of femtosecond laser intensity and multiple laser pulses on various spatial-temporal parameters. Four distinct sequences of regimes have been identified, depending on early and late times: bubble creation by individual laser pulses, coalescence, bubble rupture and expansion, and droplet fragmentation. At all laser intensities, early-time dynamics showed only bubble generation, while specifically at higher intensities, late-time dynamics revealed droplet breaking. The droplet breakup is further categorized into three mechanisms: steady sheet collapse, unstable sheet breakup, and catastrophic breakup, all following a well-known ligament and secondary breakup process. The study reveals that laser pulses with high repetition rates and moderate laser energy were the optimal choice for precise bubble control and cutting.

Simultaneous rotary and linear displacement sensor based on soft pneumatic sensing chambers

Specific industrial or research applications necessitate specialized displacement measurement conditions, thereby driving researchers to innovate sensors based on novel operating principles. One such challenging condition is the prevalence of strong electromagnetic waves, which precludes using any sensor with a metallic structure or one that operates on electrical measurement principles. Additionally, space constraints in applications requiring multidimensional displacement measurements mandate the development of sensors capable of measuring displacements simultaneously in multiple directions. This paper introduces a novel soft sensor designed to simultaneously measure linear and rotational displacements using Soft Pneumatic Sensing Chambers (SPSCs). This sensor is unique in its ability to measure both linear and rotational movements and, due to its Electro-Magnetic Compatibility (EMC) and compact size, is suitable for environments with significant electromagnetic interference and spatial constraints. Furthermore, its flexibility makes it appropriate for body-interacting applications. The Abaqus software was employed to optimize the operating parameters. Subsequently, a laboratory setup was assembled, and the sensor's performance was assessed using two calibration methods: mathematical modeling and machine learning. According to the machine learning method, the accuracy in the linear and rotational directions was 0.49 mm and 5.4°, while the Root Mean Square Error (RMSE) was 0.05mm and 0.48°, respectively.

Tetris-inspired detector with neural network for radiation mapping

Radiation mapping has attracted widespread research attention and increased public concerns on environmental monitoring. Regarding materials and their configurations, radiation detectors have been developed to identify the position and strength of the radioactive sources. However, due to the complex mechanisms of radiation-matter interaction and data limitation, high-performance and low-cost radiation mapping is still challenging. Here, we present a radiation mapping framework using Tetris-inspired detector pixels. Applying inter-pixel padding for enhancing contrast between pixels and neural networks trained with Monte Carlo (MC) simulation data, a detector with as few as four pixels can achieve high-resolution directional prediction. A moving detector with Maximum a Posteriori (MAP) further achieved radiation position localization. Field testing with a simple detector has verified the capability of the MAP method for source localization. Our framework offers an avenue for high-quality radiation mapping with simple detector configurations and is anticipated to be deployed for real-world radiation detection.

Cosine similarity knowledge distillation for surface anomaly detection

The current state-of-the-art anomaly detection methods based on knowledge distillation (KD) typically depend on smaller student networks or reverse distillation to address vanishing representations discrepancy on anomalies. These methods often struggle to achieve precise detection when dealing with complex texture backgrounds containing anomalies due to the similarity between anomalous and non-anomalous regions. Therefore, we propose a new paradigm-Cosine Similarity Knowledge Distillation (CSKD), for surface anomaly detection and localization. We focus on the superior performance of the same deeper teacher and student encoders by the distillation loss in traditional knowledge distillation-based methods. Essentially, we introduce the Attention One-Class Embedding (AOCE) in the student network to enhance learning capabilities and reduce the effect of the teacher-student (T-S) model on response similarity in anomalous regions. Furthermore, we find the optimal models by different classes' hard-coded epochs, and an adaptive optimal model selection method is designed. Extensive experiments on the MVTec dataset with 99.2% image-level AUROC and 98.2%/94.7% pixel-level AUROC/PRO demonstrate that our method outperforms existing unsupervised anomaly detection algorithms. Additional experiments on DAGM dataset, and one-class anomaly detection benchmarks further show the superiority of the proposed method.

Thermodiffusive desalination

Desalination could solve the grand challenge of water scarcity, but materials-based and conventional thermal desalination methods generally suffer from scaling, fouling and materials degradation. Here, we propose and assess thermodiffusive desalination (TDD), a method that operates entirely in the liquid phase and notably excludes evaporation, freezing, membranes, or ion-adsorbing materials. Thermodiffusion is the migration of species under a temperature gradient and can be driven by thermal energy ubiquitous in the environment. Experimentally, a 450 ppm concentration drop was achieved by thermodiffusive separation when passing a NaCl/H2O solution through a single channel. This was further increased through re-circulation as a proof of concept for TDD. We also demonstrate via molecular dynamics and experiments that TDD in multi-component seawater is more amenable than in binary NaCl/H2O solutions. Numerically, we show that a scalable cascaded channel structure can further amplify thermodiffusive separation, achieving a concentration drop of 25000 ppm with a recovery rate of 10%. The minimum electric power consumption in this setup can be as low as 3 Whe m-3, which is only 1% of the theoretical minimum energy for desalination. TDD has potential in areas with abundant thermal energy but limited electrical power resources and can contribute to alleviating global freshwater scarcity.

Wide field-of-hearing metalens for aberration-free sound capture

Metalenses are instruments that manipulate waves and have exhibited remarkable capabilities to date. However, an important hurdle arises due to the severe hampering of the angular response originating from coma and field curvature aberrations, which result in a loss of focusing ability. Herein, we provide a blueprint by introducing the notion of a wide field-of-hearing (FOH) metalens, designed particularly for capturing and focusing sound with decreased aberrations. Employing an aberration-free planar-thin metalens that leverages perfect acoustic symmetry conversion, we experimentally realize a robust wide FOH capability of approximately 140∘ in angular range. Moreover, our metalens features a relatively short focal length, enabling compact implementation by reducing the aperture-to-hearing plane distance. This is beneficial for space-efficient source-tracking sound sensing. Our strategy can be used across various platforms, potentially including energy harvesting, monitoring, imaging, and communication in auditory, ultrasonic, and submerged environments.

Gradient matters via filament diameter-adjustable 3D printing

Gradient matters with hierarchical structures endow the natural world with excellent integrity and diversity. Currently, direct ink writing 3D printing is attracting tremendous interest, and has been used to explore the fabrication of 1D and 2D hierarchical structures by adjusting the diameter, spacing, and angle between filaments. However, it is difficult to generate complex 3D gradient matters owing to the inherent limitations of existing methods in terms of available gradient dimension, gradient resolution, and shape fidelity. Here, we report a filament diameter-adjustable 3D printing strategy that enables conventional extrusion 3D printers to produce 1D, 2D, and 3D gradient matters with tunable heterogeneous structures by continuously varying the volume of deposited ink on the printing trajectory. In detail, we develop diameter-programmable filaments by customizing the printing velocity and height. To achieve high shape fidelity, we specially add supporting layers at needed locations. Finally, we showcase multi-disciplinary applications of our strategy in creating horizontal, radial, and axial gradient structures, letter-embedded structures, metastructures, tissue-mimicking scaffolds, flexible electronics, and time-driven devices. By showing the potential of this strategy, we anticipate that it could be easily extended to a variety of filament-based additive manufacturing technologies and facilitate the development of functionally graded structures.

Integrated mechanical computing for autonomous soft machines

Mechanical computing offers a new modality to formulate computational autonomy in intelligent matter or machines without any external powering or active elements. Transition (or solitary) waves, induced by nonreciprocity in mechanical metamaterials comprising a chain of bistable elements, have proven to be a key ingredient for dissipation-free transmission and computation of mechanical information. However, advanced processing of mechanical information in existing designs is hindered by its dissipation when interacting with networked logic gates. Here, we present a metamaterial design strategy that allows non-dispersive mechanical solitary waves to compute multi-level cascaded logic functions, termed 'integrated mechanical computing', by propagating through a network of structurally heterogeneous computing units. From a perspective of characteristic potential energy, we establish an analytical framework that helps in understanding the solitary wave-based mechanical computation, and governs the mechanical design of key determinants for realizing cascaded logic computation, such as soliton profile and logic elements. The developed integrated mechanical computing systems are shown to receive, transmit and compute mechanical information to actuate intelligent soft machine prototypes in a seamless and integrated manner. These findings would pave the way for future intelligent robots and machines that perform computational operations between various non-electrical environmental inputs.

A framework for design optimization across multiple concepts

In engineering design, there often exist multiple conceptual solutions to a given problem. Concept design and selection is the first phase of the design process that is estimated to affect up to 70% of the life cycle cost of a product. Currently, optimization methods are rarely used in this phase, since standard optimization methods inherently assume a fixed (given) concept; and undertaking a full-fledged optimization for each possible concept is untenable. In this paper, we aim to address this gap by developing a framework that searches for optimum solutions efficiently across multiple concepts, where each concept may be defined using a different number, or type, of variables (continuous, binary, discrete, categorical etc.). The proposed approach makes progressive data-driven decisions regarding which concept(s) and corresponding solution(s) should be evaluated over the course of search, so as to minimize the computational budget spent on less promising concepts, as well as ensuring that the search does not prematurely converge to a non-optimal concept. This is achieved through the use of a tree-structured Parzen estimator (TPE) based sampler in addition to Gaussian process (GP), and random forest (RF) regressors. Aside from extending the use of GP and RF to search across multiple concepts, this study highlights the previously unexplored benefits of TPE for design optimization. The performance of the approach is demonstrated using diverse case studies, including design of a cantilever beam, coronary stents, and lattice structures using a limited computational budget. We believe this contribution fills an important gap and capitalizes on the developments in the machine learning domain to support designers involved in concept-based design.

3D nanofabricated soft microrobots with super-compliant picoforce springs as onboard sensors and actuators

Microscale organisms and specialized motile cells use protein-based spring-like responsive structures to sense, grasp and move. Rendering this biomechanical transduction functionality in an artificial micromachine for applications in single-cell manipulations is challenging due to the need for a bio-applicable nanoscale spring system with a large and programmable strain response to piconewton-scale forces. Here we present three-dimensional nanofabrication and monolithic integration, based on an acrylic elastomer photoresist, of a magnetic spring system with quantifiable compliance sensitive to 0.5 pN, constructed with customized elasticity and magnetization distributions at the nanoscale. We demonstrate the effective design programmability of these 'picospring' ensembles as energy transduction mechanisms for the integrated construction of customized soft micromachines, with onboard sensing and actuation functions at the single-cell scale for microrobotic grasping and locomotion. The integration of active soft springs into three-dimensional nanofabrication offers an avenue to create biocompatible soft microrobots for non-disruptive interactions with biological entities.

Surface defect detection of hot rolled steel based on multi-scale feature fusion and attention mechanism residual block

To improve the precision of defect categorization and localization in images, this paper proposes an approach for detecting surface defects in hot-rolled steel strips. The approach uses an improved YOLOv5 network model to overcome the issues of inadequate feature extraction capacity and suboptimal feature integration when identifying surface defects on steel strips. The proposed method achieves higher detection accuracy and localization precision, making it more competitive and applicable in real production. Firstly, the multi-scale feature fusion (MSF) strategy is utilized to fuse shallow and deep features effectively and enrich detailed information relevant to target defects. Secondly, the CSPLayer Res2Attention block (CRA block) residual module is introduced to reduce the loss of defect information during hierarchical transmission, thereby enhancing the extraction of fine-grained features and improving the perception of details and global features. Finally, the experimental results indicate that the mAP on the NEU-DET and GC10-DET datasets approaches 78.5% and 67.3%, respectively, which is 4.9% and 2.1% higher than that of the baseline. Meanwhile, it has higher precision and more precise localization capabilities than other methods. Furthermore, it also achieves 59.2% mAP on the APDDD dataset, indicating its potential for growth in further domains.

Quantitative, high-sensitivity measurement of liquid analytes using a smartphone compass

Smartphone ubiquity has led to rapid developments in portable diagnostics. While successful, such platforms are predominantly optics-based, using the smartphone camera as the sensing interface. By contrast, magnetics-based modalities exploiting the smartphone compass (magnetometer) remain unexplored, despite inherent advantages in optically opaque, scattering or auto-fluorescing samples. Here we report smartphone analyte sensing utilizing the built-in magnetometer for signal transduction via analyte-responsive magnetic-hydrogel composites. As these hydrogels dilate in response to targeted stimuli, they displace attached magnetic material relative to the phone's magnetometer. Using a bilayer hydrogel geometry to amplify this motion allows for sensitive, optics-free, quantitative liquid-based analyte measurements that require neither any electronics nor power beyond that contained within the smartphone itself. We demonstrate this concept with glucose-specific and pH-responsive hydrogels, including glucose detection down to single-digit micromolar concentrations with potential for extension to nanomolar sensitivities. The platform is adaptable to numerous measurands, opening a path towards portable, inexpensive sensing of multiple analytes or biomarkers of interest.

Optimal blade pitch control for enhanced vertical-axis wind turbine performance

Vertical-axis wind turbines are great candidates to enable wind power extraction in urban and off-shore applications. Currently, concerns around turbine efficiency and structural integrity limit their industrial deployment. Flow control can mitigate these concerns. Here, we experimentally demonstrate the potential of individual blade pitching as a control strategy and explain the flow physics that yields the performance enhancement. We perform automated experiments using a scaled-down turbine model coupled to a genetic algorithm optimiser to identify optimal pitching kinematics at on- and off-design operating conditions. We obtain two sets of optimal pitch profiles that achieve a three-fold increase in power coefficient at both operating conditions compared to the non-actuated turbine and a 77% reduction in structure-threatening load fluctuations at off-design conditions. Based on flow field measurements, we uncover how blade pitching manipulates the flow structures to enhance performance. Our results can aid vertical-axis wind turbines increase their much-needed contribution to our energy needs.

High-efficiency and low-hazard artillery recoil reduction technology based on barrel gas reflection

Reducing recoil as well as reducing muzzle hazards are important issues in artillery design. This paper presents a barrel gas reflection method for the artillery aiming for efficient recoil reduction while reducing muzzle hazards. The launching process is modeled by coupling the interior ballistic equations and the flow equations of the barrel gas reflection device. The fourth-order Runge-Kutta method was used to solve the model, and the LHS method as well as the Kriging model was used to establish a mapping relationship between the parameters and the effect. To validate the proposed model, shooting experiments are carried out on a 30 mm caliber artillery. The maximum error between the experiment and simulation results was 5.32%. The experiment has demonstrated that the barrel gas reflection method increases the recoil reduction efficiency of artillery by 44.54% and reduces the muzzle hazard by 52.18%. Finally, the barrel gas reflection method can produce effects with the muzzle device at the same time, and it has little effect on the velocity of the projectile muzzle velocity, and it provides a new way of thinking for the development of future artillery recoil reduction technology.

Microstructural and mechanical characterization of Al/Cu interface in a bimetallic composite produced by compound casting

The bimetal set (Al/Cu) with Cu wire with 2.0, 2.5, and 3.0 mm diameters were cast at different casting temperatures and solidification times through the compound casting method. The microstructure of solid/liquid diffusion bonding at the Al/Cu interface was investigated, and the shear strength of the Al/Cu interface was measured by punch test. By characterizing the diffusion layer, the optimum parameters of the compound casting, including the casting temperature and the solidification soaking time, as well as the Cu wire diameter, were acquired. The intermetallic compounds (IMCs) such as CuAl2 were observed in the diffusion layer. The types of intermetallic phases and diffusion layer thickness affect the hardness and the shear strength. The result of casting at 680 °C and solidification soaking time of 15 s for 3 mm Cu wire, shows that IMCs increased the micro-hardness of the Al/Cu bimetal up to 328 HV at the Al/Cu interface. Also, increasing the solidification soaking time at a constant temperature resulted in a growth of the interface layer's thickness, which exhibits a lamellar eutectic microstructure containing IMCs. Furthermore, this action caused an increase in the shear strength.

Programming mechanics in knitted materials, stitch by stitch

Knitting turns yarn, a 1D material, into a 2D fabric that is flexible, durable, and can be patterned to adopt a wide range of 3D geometries. Like other mechanical metamaterials, the elasticity of knitted fabrics is an emergent property of the local stitch topology and pattern that cannot solely be attributed to the yarn itself. Thus, knitting can be viewed as an additive manufacturing technique that allows for stitch-by-stitch programming of elastic properties and has applications in many fields ranging from soft robotics and wearable electronics to engineered tissue and architected materials. However, predicting these mechanical properties based on the stitch type remains elusive. Here we untangle the relationship between changes in stitch topology and emergent elasticity in several types of knitted fabrics. We combine experiment and simulation to construct a constitutive model for the nonlinear bulk response of these fabrics. This model serves as a basis for composite fabrics with bespoke mechanical properties, which crucially do not depend on the constituent yarn.

Experimental design of 4-point supported belt robot for sanding large convex surfaces

In general, sanding robots that move as if drawing a line along a surface are mainly used when sanding objects with a large area; however, they require a long working time, and it is difficult to secure a uniform sanded area. This study focuses on large-area sanding robots, such as those for ships, storage tanks, and tank lorries, and proposes an adaptive belt tension robot equipped with a 4-point supported belt mechanism capable of sanding variable curved surfaces. In addition, a sanding normal force prediction formula is proposed to describe the sanding performance of the contact surface. This equation consists of the concentrated load function due to the belt movement and the normal force due to the vertical and horizontal elongation of the belt. A video image analysis was performed to calculate the sanding area. Therefore, we determined whether the area was uniformly sanded. The dimensions of the test bench (W × D × H) were 1700 mm × 1450 mm × 900 mm. Experiments were performed using the proposed techniques on convex specimens with radii of 725, 1000, and 2100 mm. The sanding performance was improved by 43 % compared with that of a general belt-sanding robot.

A Dataset of Electrical Components for Mesh Segmentation and Computational Geometry Research

Data quality is of crucial importance in the field of automated or digitally assisted assembly. This paper presents a comprehensive data set of triangle meshes representing electrical and electronic components obtained by scraping Computer Aided Design (CAD) models from the Internet. Consisting of a total of 234 triangle meshes with labelled vertices, this data set was specifically created for segmentation tasks. Its versatility for multimodal tasks is underscored by the presence of various labels, including vertex labels, categories, and subcategories. This paper presents the data set and provides a thorough statistical analysis, including measures of shape, size, distribution, and inter-rater reliability. In addition, the paper suggests several approaches for using the data set, considering its multimodal characteristics. The data set and related findings presented in this paper are intended to encourage further research and advancement in the field of manufacturing automation, specifically spatial assembly.

Role of compliant mechanics and motor control in hopping - from human to robot

Compliant leg function found during bouncy gaits in humans and animals can be considered a role model for designing and controlling bioinspired robots and assistive devices. The human musculoskeletal design and control differ from distal to proximal joints in the leg. The specific mechanical properties of different leg parts could simplify motor control, e.g., by taking advantage of passive body dynamics. This control embodiment is complemented by neural reflex circuitries shaping human motor control. This study investigates the contribution of specific passive and active properties at different leg joint levels in human hopping at different hopping frequencies. We analyze the kinematics and kinetics of human leg joints to design and control a bioinspired hopping robot. In addition, this robot is used as a test rig to validate the identified concepts from human hopping. We found that the more distal the joint, the higher the possibility of benefit from passive compliant leg structures. A passive elastic element nicely describes the ankle joint function. In contrast, a more significant contribution to energy management using an active element (e.g., by feedback control) is predicted for the knee and hip joints. The ankle and knee joints are the key contributors to adjusting hopping frequency. Humans can speed up hopping by increasing ankle stiffness and tuning corresponding knee control parameters. We found that the force-modulated compliance (FMC) as an abstract reflex-based control beside a fixed spring can predict human knee torque-angle patterns at different frequencies. These developed bioinspired models for ankle and knee joints were applied to design and control the EPA-hopper-II robot. The experimental results support our biomechanical findings while indicating potential robot improvements. Based on the proposed model and the robot's experimental results, passive compliant elements (e.g. tendons) have a larger capacity to contribute to the distal joint function compared to proximal joints. With the use of more compliant elements in the distal joint, a larger contribution to managing energy changes is observed in the upper joints.

Fast Human Motion reconstruction from sparse inertial measurement units considering the human shape

Inertial Measurement Unit-based methods have great potential in capturing motion in large-scale and complex environments with many people. Sparse Inertial Measurement Unit-based methods have more research value due to their simplicity and flexibility. However, improving the computational efficiency and reducing latency in such methods are challenging. In this paper, we propose Fast Inertial Poser, which is a full body motion estimation deep neural network based on 6 inertial measurement units considering body parameters. We design a network architecture based on recurrent neural networks according to the kinematics tree. This method introduces human body shape information by the causality of observations and eliminates the dependence on future frames. During the estimation of joint positions, the upper body and lower body are estimated using separate network modules independently. Then the joint rotation is obtained through a well-designed single-frame kinematics inverse solver. Experiments show that the method can greatly improve the inference speed and reduce the latency while ensuring the reconstruction accuracy compared with previous methods. Fast Inertial Poser runs at 65 fps with 15 ms latency on an embedded computer, demonstrating the efficiency of the model.

Large-scale modular and uniformly thick origami-inspired adaptable and load-carrying structures

Existing Civil Engineering structures have limited capability to adapt their configurations for new functions, non-stationary environments, or future reuse. Although origami principles provide capabilities of dense packaging and reconfiguration, existing origami systems have not achieved deployable metre-scale structures that can support large loads. Here, we established modular and uniformly thick origami-inspired structures that can deploy into metre-scale structures, adapt into different shapes, and carry remarkably large loads. This work first derives general conditions for degree-N origami vertices to be flat foldable, developable, and uniformly thick, and uses these conditions to create the proposed origami-inspired structures. We then show that these origami-inspired structures can utilize high modularity for rapid repair and adaptability of shapes and functions; can harness multi-path folding motions to reconfigure between storage and structural states; and can exploit uniform thickness to carry large loads. We believe concepts of modular and uniformly thick origami-inspired structures will challenge traditional practice in Civil Engineering by enabling large-scale, adaptable, deployable, and load-carrying structures, and offer broader applications in aerospace systems, space habitats, robotics, and more.

Electrothermally controlled origami fabricated by 4D printing of continuous fiber-reinforced composites

Active origami capable of precise deployment control, enabling on-demand modulation of its properties, is highly desirable in multi-scenario and multi-task applications. While 4D printing with shape memory composites holds great promise to realize such active origami, it still faces challenges such as low load-bearing capacity and limited transformable states. Here, we report a fabrication-design-actuation method of precisely controlled electrothermal origami with excellent mechanical performance and spatiotemporal controllability, utilizing 4D printing of continuous fiber-reinforced composites. The incorporation of continuous carbon fibers empowers electrothermal origami with a controllable actuation process via Joule heating, increased actuation force through improved heat conduction, and enhanced mechanical properties as a result of reinforcement. By modeling the multi-physical and highly nonlinear deploying process, we attain precise control over the active origami, allowing it to be reconfigured and locked into any desired configuration by manipulating activation parameters. Furthermore, we showcase the versatility of electrothermal origami by constructing reconfigurable robots, customizable architected materials, and programmable wings, which broadens the practical engineering applications of origami.

Ammonia marine engine design for enhanced efficiency and reduced greenhouse gas emissions

Pilot-diesel-ignition ammonia combustion engines have attracted widespread attentions from the maritime sector, but there are still bottleneck problems such as high unburned NH3 and N2O emissions as well as low thermal efficiency that need to be solved before further applications. In this study, a concept termed as in-cylinder reforming gas recirculation is initiated to simultaneously improve the thermal efficiency and reduce the unburned NH3, NOx, N2O and greenhouse gas emissions of pilot-diesel-ignition ammonia combustion engine. For this concept, one cylinder of the multi-cylinder engine operates rich of stoichiometric and the excess ammonia in the cylinder is partially decomposed into hydrogen, then the exhaust of this dedicated reforming cylinder is recirculated into the other cylinders and therefore the advantages of hydrogen-enriched combustion and exhaust gas recirculation can be combined. The results show that at 3% diesel energetic ratio and 1000 rpm, the engine can increase the indicated thermal efficiency by 15.8% and reduce the unburned NH3 by 89.3%, N2O by 91.2% compared to the base/traditional ammonia engine without the proposed method. At the same time, it is able to reduce carbon footprint by 97.0% and greenhouse gases by 94.0% compared to the traditional pure diesel mode.

Pore-scale physics of ice melting within unconsolidated porous media revealed by non-destructive magnetic resonance characterization

Melting of ice in porous media widely exists in energy and environment applications as well as extraterrestrial water resource utilization. In order to characterize the ice-water phase transition within complicated opaque porous media, we employ the nuclear magnetic resonance (NMR) and imaging (MRI) approaches. Transient distributions of transverse relaxation time T2 from NMR enable us to reveal the substantial role of inherent throat and pore confinements in ice melting among porous media. More importantly, the increase in minimum T2 provides new findings on how the confinement between ice crystal and particle surface evolves inside the pore. For porous media with negligible gravity effect, both the changes in NMR-determined melting rate and our theoretical analysis of melting front confirm that conduction is the dominant heat transfer mode. The evolution of mushy melting front and 3D spatial distribution of water content are directly visualized by a stack of temporal cross-section images from MRI, in consistency with the corresponding NMR results. For heterogeneous porous media like lunar regolith simulant, the T2 distribution shows two distinct pore size distributions with different pore-scale melting dynamics, and its maximum T2 keeps increasing till the end of melting process instead of reaching steady in homogeneous porous media.

Wood-inspired metamaterial catalyst for robust and high-throughput water purification

Continuous industrialization and other human activities have led to severe water quality deterioration by harmful pollutants. Achieving robust and high-throughput water purification is challenging due to the coupling between mechanical strength, mass transportation and catalytic efficiency. Here, a structure-function integrated system is developed by Douglas fir wood-inspired metamaterial catalysts featuring overlapping microlattices with bimodal pores to decouple the mechanical, transport and catalytic performances. The metamaterial catalyst is prepared by metal 3D printing (316 L stainless steel, mainly Fe) and electrochemically decorated with Co to further boost catalytic functionality. Combining the flexibility of 3D printing and theoretical simulation, the metamaterial catalyst demonstrates a wide range of mechanical-transport-catalysis capabilities while a 70% overlap rate has 3X more strength and surface area per unit volume, and 4X normalized reaction kinetics than those of traditional microlattices. This work demonstrates the rational and harmonious integration of structural and functional design in robust and high throughput water purification, and can inspire the development of various flow catalysts, flow batteries, and functional 3D-printed materials.

Reproduction of forearm rotation dynamic using intensity-based biplane 2D-3D registration matching method

This study aimed to reproduce and analyse the in vivo dynamic rotational motion of the forearm and to clarify forearm motion involvement and the anatomical function of the interosseous membrane (IOM). The dynamic forearm rotational motion of the radius and ulna was analysed in vivo using a novel image-matching method based on fluoroscopic and computed tomography images for intensity-based biplane two-dimensional-three-dimensional registration. Twenty upper limbs from 10 healthy volunteers were included in this study. The mean range of forearm rotation was 150 ± 26° for dominant hands and 151 ± 18° for non-dominant hands, with no significant difference observed between the two. The radius was most proximal to the maximum pronation relative to the ulna, moved distally toward 60% of the rotation range from maximum pronation, and again proximally toward supination. The mean axial translation of the radius relative to the ulna during forearm rotation was 1.8 ± 0.8 and 1.8 ± 0.9 mm for dominant and non-dominant hands, respectively. The lengths of the IOM components, excluding the central band (CB), changed rotation. The transverse CB length was maximal at approximately 50% of the rotation range from maximum pronation. Summarily, this study describes a detailed method for evaluating in vivo dynamic forearm motion and provides valuable insights into forearm kinematics and IOM function.

Flame self-interactions in MILD combustion of homogeneous and inhomogeneous mixtures

Flame self-interaction (FSI) events in Moderate or Intense Low-Oxygen Dilution (MILD) combustion of homogeneous and inhomogeneous mixtures of methane and oxidiser have been analysed using three-dimensional Direct Numerical Simulations (DNS). The simulations have been conducted at the same global equivalence ratio ( ⟨ ϕ ⟩ = 0.8 ) for different levels of O 2 concentration (dilution) and initial turbulence intensities. It has been reported that both homogeneous and inhomogeneous mixture MILD combustion cases exhibit significant occurrences of FSI events, with the peak frequency of FSI events occurring towards the burned gas side in all cases. Moreover, the frequency of FSI events increases with increasing dilution level and turbulence intensity, but the presence of mixture inhomogeneity leads to a reduction in total FSI events. In all cases, the cylindrical FSI topologies (i.e. tunnel formation and tunnel closure) were found to have a higher likelihood of occurrence compared to spherical FSI topologies (i.e. unburned and burned gas pockets). The geometries of FSI topologies were also analysed using the mean and Gaussian curvatures. It has been shown that the inward propagating spherical FSI topologies (i.e. unburned gas pockets) are associated with negative mean curvature, while outward propagating spherical FSI topologies (i.e. burned gas pockets) are associated with positive mean curvature. Moreover, tunnel formation (tunnel closure) FSI topologies predominantly exhibit either elliptic geometries with positive (negative) mean curvature or hyperbolic saddle geometries with negative (positive) mean curvature. It has been shown for the first time in MILD combustion that the mean values of kinematic restoration and dissipation terms in the transport equation of the magnitude of the reaction progress variable conditional upon the reaction progress variable tend to cancel each other in the vicinity of the critical points associated with cylindrical topologies. Thus, the singular contributions in these terms, which are obtained from analytical descriptions in the vicinity of tunnel formation and tunnel closure topologies, do not affect the balance equation of the magnitude of the gradient of the reaction progress variable. Consequently, there is no need for a separate model treatment for singularities in modelling approaches based on the magnitude of the gradient of the reaction progress variable. The FSI events in the reaction dominated and propagating flame regions of MILD combustion have also been analysed for the first time. It has been found that more FSI events occur in the reaction dominated region, particularly towards the burned gas side. However, the majority of spherical FSI topologies are found in the propagating flame region. The findings from this study indicate that turbulence intensity, dilution level and mixture inhomogeneity effects need to be considered in any attempt to extend flame surface-based modelling approaches to MILD combustion.

Research on fabric surface defect detection algorithm based on improved Yolo_v4

In industry, the task of defect classification and defect localization is an important part of defect detection system. However, existing studies only focus on one task and it is difficult to ensure the accuracy of both tasks. This paper proposes a defect detection system based on improved Yolo_v4, which greatly improves the detection ability of minor defects. For K_Means algorithm clustering prianchors question with strong subjectivity, the paper proposes the Density Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to determine the number of Anchors. To solve the problem of low detection rate of small targets caused by insufficient reuse rate of low-level features in CSPDarknet53 feature extraction network, this paper proposes an ECA-DenseNet-BC-121 feature extraction network to improve it. And the Dual Channel Feature Enhancement (DCFE) module is proposed to improve the local information loss and gradient propagation obstruction caused by quad chain convolution in PANet networks to improve the robustness of the model. The experimental results on the fabric surface defect detection datasets show that the mAP of the improved Yolo_v4 is 98.97%, which is 7.67% higher than SSD, 3.75% higher than Faster_RCNN, 10.82% higher than Yolo_v4 tiny, and 5.35% higher than Yolo_v4, and the detection speed reaches 39.4 fps. It can meet the real-time monitoring needs of industrial sites.

Social perception of robots is shaped by beliefs about their minds

Roboticists often imbue robots with human-like physical features to increase the likelihood that they are afforded benefits known to be associated with anthropomorphism. Similarly, deepfakes often employ computer-generated human faces to attempt to create convincing simulacra of actual humans. In the present work, we investigate whether perceivers' higher-order beliefs about faces (i.e., whether they represent actual people or android robots) modulate the extent to which perceivers deploy face-typical processing for social stimuli. Past work has shown that perceivers' recognition performance is more impacted by the inversion of faces than objects, thus highlighting that faces are processed holistically (i.e., as Gestalt), whereas objects engage feature-based processing. Here, we use an inversion task to examine whether face-typical processing is attenuated when actual human faces are labeled as non-human (i.e., android robot). This allows us to employ a task shown to be differentially sensitive to social (i.e., faces) and non-social (i.e., objects) stimuli while also randomly assigning face stimuli to seem real or fake. The results show smaller inversion effects when face stimuli were believed to represent android robots compared to when they were believed to represent humans. This suggests that robots strongly resembling humans may still fail to be perceived as "social" due pre-existing beliefs about their mechanistic nature. Theoretical and practical implications of this research are discussed.

A new model for compressor surge and stall control

This paper compares the bifurcations and closed-loop performances of two compressor models, Moore-Greitzer (MG) and a developed model based on MG (Shahriyari Khaleghi, SK). First, both models are linearized about two equilibrium points (pure surge and fully-developed rotating stall), and the perturbed state-space dynamics and input matrices are obtained. The compressor unstable regions are then identified using an eigenvalue and global bifurcation analysis. Furthermore, optimal LQR controllers are designed, and the performances of closed-loop systems are compared. The LQRs are designed to control the compression system near the peak pressure rise by suppressing surge or stall. Results reveal that if the initial operating point is in the positive slope region of the compressor characteristic and the initial amplitude of the disturbances is small, the LQR controller can stabilize the compressor in both models. However, when the disturbances are intensive, the two models respond differently: although the SK model damps a fair range of disturbances and predicts instability for excessively powerful disturbances, the MG model always damps them, even when extremely intense. Without a controller in the MG model, initial disturbances (even very large) can never grow and are always damped in the compressor's negative slope region (obviously, the same applies to the controller). However, pending the amplitude of the disturbances (in the absence of a controller), the disturbances in the SK model may be damped or grow. The SK model can successfully control the instabilities if the disturbances are small. Nonetheless, the controller fails to dampen the instabilities for extreme disturbances, which is consistent with reality.

Electromagnetic forming of AA1060 sheet based on mixed forces generated by a three-coil dual-power system

The electromagnetic force used in electromagnetic forming is mainly divided into attraction and repulsion. Dual-coil attractive electromagnetic forming can be used in the field of sheet pit repair. However, the magnetic field and eddy current generated by the two coils compete with each other, and the energy utilization rate is low. Therefore, a compensation coil is introduced, and an electromagnetic forming scheme of a three-coil dual-power sheet based on mixed force is proposed and verified by simulation. It is found that the three-coil mixed force can effectively improve the competition between the magnetic field and eddy current. The loading of the mixing force is not a simple superposition of attraction and repulsion, but the mutual promotion of the two. The forming displacement of the three-coil mixed force forming scheme is 582% higher than that of the dual-coil attraction forming scheme, and 89% higher than that of the attract first and then repel forming scheme. The forming effect of the three-coil mixing force is related to the number of turns of the compensation coil. The research results can improve the energy utilization rate of electromagnetic forming and provide a new idea for the loading scheme of electromagnetic forming force field.

Muscle-inspired bi-planar cable routing: a novel framework for designing cable driven lower limb rehabilitation exoskeletons (C-LREX)

There is a growing interest in the research and development of Cable Driven Rehabilitation Devices (CDRDs) due to multiple inherent features attractive to clinical applications, including low inertia, lightweight, high payload-to-weight ratio, large workspace, and modular design. However, previous CDRDs have mainly focused on modifying motor impairment in the sagittal plane, despite the fact that neurological disorders, such as stroke, often involve postural control and gait impairment in multiple planes. To address this gap, this work introduces a novel framework for designing a cable-driven lower limb rehabilitation exoskeleton which can assist with bi-planar impaired posture and gait. The framework used a lower limb model to analyze different cable routings inspired by human muscle architecture and attachment schemes to identify optimal routing and associated parameters. The selected cable routings were safeguarded for non-interference with the human body while generating bi-directional joint moments. The subsequent optimal cable routing model was then implemented in simulations of tracking reference healthy trajectory with bi-planar impaired gait (both in the sagittal and frontal planes). The results showed that controlling joints independently via cables yielded better performance compared to dependent control. Routing long cables through intermediate hinges reduced the peak tensions in the cables, however, at a cost of induced additional joint forces. Overall, this study provides a systematic and quantitative in silico approach, featured with accessible graphical user interface (GUI), for designing subject-specific, safe, and effective lower limb cable-driven exoskeletons for rehabilitation with options for multi-planar personalized impairment-specific features.

IInception-CBAM-IBiGRU based fault diagnosis method for asynchronous motors

Aiming at the problems of insufficient extraction of asynchronous motor fault features by traditional deep learning algorithms and poor diagnosis of asynchronous motor faults in robust noise environments, this paper proposes an end-to-end fault diagnosis method for asynchronous motors based on IInception-CBAM-IBiGRU. The method first uses a signal-to-grayscale image conversion method to convert one-dimensional vibration signals into two-dimensional images and initially extracts shallow features through two-dimensional convolution; then the Improved Inception (IInception) module is used as a residual block to learning features at different scales with a residual structure, and extracts its important feature information through the Convolutional Block Attention Module (CBAM) to extract important feature information and adjust the weight parameters; then the feature information is input to the Improved Bi-directional Gate Recurrent Unit (IBiGRU) to extract its timing features further; finally, the fault identification is achieved by the SoftMax function. The primary hyperparameters in the model are optimized by the Weighted Mean Of Vectors Algorithm (INFO). The experimental results show that the method is effective in fault diagnosis of asynchronous motors, with an accuracy rate close to 100%, and can still maintain a high accuracy rate under the condition of low noise ratio, with good robustness and generalization ability.

A PLC-based pomegranate sprout removal device design

Aiming at the current low degree of mechanization of pomegranate sprouting tiller pruning in China, all relying on manual pruning, this paper designs a PLC-based pomegranate sprouting tiller removal machine. This machine adopts the identification method of wireless map transmission, the sprouting tiller removal method of multi-cylinder cooperative operation, and the MCGS configuration to realize the interaction between the user and the system, which realizes the displacement and angle compensation of the end-effector under complex conditions to realize the all-around accurate removal of the pomegranate sprouting tiller. The performance test and finite element analysis showed that the device could remove up to 74.62% of sprouting tillers, and the damage rate was as low as 18%. This meets the requirements of pomegranate plantations for the removal of emergent tillers.